English

PyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture

Computer Vision and Pattern Recognition 2022-01-05 v1

Abstract

Transformer networks have achieved great progress for computer vision tasks. Transformer-in-Transformer (TNT) architecture utilizes inner transformer and outer transformer to extract both local and global representations. In this work, we present new TNT baselines by introducing two advanced designs: 1) pyramid architecture, and 2) convolutional stem. The new "PyramidTNT" significantly improves the original TNT by establishing hierarchical representations. PyramidTNT achieves better performances than the previous state-of-the-art vision transformers such as Swin Transformer. We hope this new baseline will be helpful to the further research and application of vision transformer. Code will be available at https://github.com/huawei-noah/CV-Backbones/tree/master/tnt_pytorch.

Keywords

Cite

@article{arxiv.2201.00978,
  title  = {PyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture},
  author = {Kai Han and Jianyuan Guo and Yehui Tang and Yunhe Wang},
  journal= {arXiv preprint arXiv:2201.00978},
  year   = {2022}
}

Comments

Tech Report. An extension of "Transformer in Transformer" (arXiv:2103.00112)

R2 v1 2026-06-24T08:39:26.364Z